List your company

Referring Video Object Segmentation on A2D Sentences v1.0 (test)

81.2IoU OverallLoSh-S
52.49659.94867.474.852Jul 26, 2022Sep 17, 2022Nov 10, 2022Jan 3, 2023Feb 26, 2023Apr 21, 2023Jun 14, 2023

Evaluation results

MethodLinks
LoSh-SBackbone=Video-Swin-B, Number of input frames (w)=52023.0681.2—————59.973.1
SgMgBackbone=Video-Swin-B, Number of input frames (w)=52023.0679.9—————58.572
LoSh-SBackbone=Video-Swin-T, Number of input frames (w)=52023.0679.3—————57.671.6
ReferFormerBackbone=Video-Swin-B2023.0678.6—————5570.3
SgMgBackbone=Video-Swin-T, Number of input frames (w)=52023.0678—————56.170.4
LoSh-MBackbone=Video-Swin-T, Number of input frames (w)=82023.0672.9—————47.864.9
LoSh-M w/ MShBackbone=Video-Swin-T2023.0672.9—————47.864.8
LoSh-M w/ Bi-CABackbone=Video-Swin-T2023.0672.8—————47.664.7
MANetVenue=-2022.0772.673.468.257.938.913.247.163.2
LoSh-M w/o CABackbone=Video-Swin-T2023.0672.5—————47.364.5
LoSh-M w/ Inv-CABackbone=Video-Swin-T2023.0672.5—————47.264.3
LoSh-M w/o LlsiBackbone=Video-Swin-T2023.0672.3—————46.163.8
LoSh-M w/o ShBackbone=Video-Swin-T2023.0671.1—————45.462.6
MTTRVenue=CVPR222022.0770.272.168.460.745.616.444.761.8
MTTRBackbone=Video-Swin-T, Number of input frames (w)=82023.0670.2—————44.761.8
CSTMVenue=CVPR212022.0766.265.458.949.733.39.139.956.1
PolarRPEVenue=IJCAI202022.0766.163.457.948.332.28.338.852.9
CMPC-VVenue=T-PAMI212022.0765.365.559.250.634.29.840.457.3
CMPC-VBackbone=I3D2023.0665.3—————40.457.3
CCMAVenue=ACMMM212022.0763.265.364.561.149.117.44855.5
CMDyVenue=AAAI202022.0762.360.752.540.523.54.533.353.1
CMSA+CFSAVenue=T-PAMI212022.0761.848.743.135.823.15.2—43.2
ACGAVenue=ICCV192022.0760.155.745.931.916227.449
VT-CapsuleVenue=CVPR202022.0756.852.64534.520.73.630.346
A2DSVenue=CVPR182022.0755.15037.623.19.40.421.542.6
Gavrilyuk et al.Backbone=I3D2023.0653.6—————19.842.1